Tokyo Kion-On: Query-Based Generative Sonification of Atmospheric Data

TL;DR

This paper introduces Tokyo Kion-On, a novel query-based sonification system that transforms Tokyo's historical air temperature data into musical representations using an LSTM model, enhancing data exploration and understanding.

Contribution

It presents a new LSTM-based sonification model conditioned on atmospheric data, enabling interactive and non-linear exploration of climate change impacts through music.

Findings

Effective transformation of temperature data into musical form.

Hyper-parameters facilitate active data exploration.

Model demonstrates potential for environmental data sonification.

Abstract

Amid growing environmental concerns, interactive displays of data constitute an important tool for exploring and understanding the impact of climate change on the planet's ecosystemic integrity. This paper presents Tokyo kion-on, a query-based sonification model of Tokyo's air temperature from 1876 to 2021. The system uses a recurrent neural network architecture known as LSTM with attention trained on a small dataset of Japanese melodies and conditioned upon said atmospheric data. After describing the model's implementation, a brief comparative illustration of the musical results is presented, along with a discussion on how the exposed hyper-parameters can promote active and non-linear exploration of the data.